Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    domains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _enter
    -0.07
    ��
    -0.07
     bolt
    -0.07
    onso
    -0.07
    forth
    -0.07
    แสดง
    -0.06
    elpers
    -0.06
     преступ
    -0.06
    Doctor
    -0.06
    'une
    -0.06
    POSITIVE LOGITS
     getDescription
    0.06
     suggestive
    0.06
     departments
    0.06
    inputEmail
    0.06
    아
    0.06
    魚
    0.06
     Huffington
    0.06
    
    0.06
     disillusion
    0.05
     acclaim
    0.05
    Act Density 0.039%

    No Known Activations